Julia Linhart
Julia Linhart
Oh i don't know why the tests fail... they pass when I run them locally! Any idea why that would be the case?
I think the `npe.sample` method (where `npe` is a `DensityEstimator` object) is different for the tests vs. on the branch I am working on. It seems to be the handling...
Oh right.. Sorry! So I fixed it, but had to reshape a lot...
I did some experiments and I was wondering how you choose the parameters for the`MLPClassifier` from `sklearn` corresponding to the default `classifier=mlp` in `c2st` and the `LC2ST` class. Especially `early_stopping`...
There you go @psteinb :) Thanks a lot for your review!
Hello everyone. I propose in this last commit a solution to the ensembling / cross-val issue stated above. - I chose to create a `EnsembleClassifier` class whose predicted probabilities are...
Thank you for your valuable comments and reviews !!
Hello! That's amazing, thanks for the initiative! 1. I’d apply `skorch` to L-C2ST or MLP-based C2ST to enable GPU acceleration 2. For RF-based C2ST, we have a few options: -...
Yes sounds good!!
Yes, so if I understand correctly (I havn't used skorch before either...) you need a PyTorch `nn.Module` to wrap the `skorch.NeuralNetClassifier` around, like this as mentioned [here](https://skorch.readthedocs.io/en/stable/user/quickstart.html): ``` class MyModule(nn.Module):...